FindcheapFindcheap
APIAbout

Introducing Findcheap

PriceBench Performance

0%25%50%75%100%0s20s40s60s80smedian search latencysavings captureFindcheap15.6s · 92.8%GPT-5.6 Sol61.5s · 45.5%Perplexity74.7s · 34.1%Gemini 3.1 Pro80s · 10.7%
PriceBench results, equivalent-product track, human-verified, N=100 products. Savings capture plotted against median search latency for the interactive agents.

Findcheap is substantially more accurate, faster, and cheaper than the frontier models. To make this fully transparent and auditable, the evals that were used to generate the metrics on this page are available in the GitHub repo. In the interest of encouraging innovation in this space, the benchmark is open source and includes a skill to run it with one prompt!

What is Findcheap?

Findcheap is an AI agent that searches the internet to find the cheapest place to buy stuff.

What makes it unique is that it thinks like a human does. It's able to find cheaper options for 94% of products on the internet, and saves users 60.4% on average.

How is Findcheap able to beat the big AI labs?

Frontier models try to be the best at everything. Findcheap tries to be the best at a narrow subfield of agentic AI: multimodal search.

While most people have never heard this term before, Findcheap was built on the thesis that several trillion-dollar companies will be built in this space. Findcheap is an early, extremely high-conviction bet that this technology will allow us to rebuild the $36 trillion e-commerce industry from first principles. Because agentic search unlocks agentic commerce.

Task: find lower-priced equivalent products

0%25%50%75%100%92.8%45.5%34.1%20.2%10.7%

Task: find exact brand/model for the lowest available price

0%25%50%75%100%79.6%37.0%20.7%24.9%10.7%

Latency

(lower is better)
0s60s120s180s240s15.6s61.5s74.7s232s80s

Cost

(lower is better)
$0.00$0.50$1.00$1.50$0.03$0.54$0.38$1.41$0.08
PriceBench N=100 human-verified results: savings capture on both tracks, median latency, and cost per search for Findcheap, GPT-5.6 Sol, Perplexity, Claude Opus 5, and Gemini 3.1 Pro.

Note: the pricing shown above is for the Findcheap API. Findcheap is completely free through the Chrome extension.

Because this technology is still early, there's no widely-used benchmark for evaluating agents’ performance on this task. That's why PriceBench was created. This benchmark is the first of its kind in a number of ways:

  • It doesn't have a fixed set of input tasks, which makes it impossible to game the benchmark by overfitting on specific tasks. Instead, it autonomously sources new input tasks at runtime.
  • It's designed to run with almost no human intervention. A panel of 3 judges composed of GPT-5.6 Sol, Claude Opus 5, and Gemini 3.5 Flash autonomously reviews results, to avoid human biases.
  • It sources tasks based on real-world data. For a benchmark to accurately reflect a real user’s experience, it must include a mix of large and small retailers, and different product categories. For example, Amazon accounts for about 42% of e-commerce sales in the US, so 42 of 100 input tasks are sourced from Amazon.

How do I use it?

Findcheap has released 2 products so far, a consumer product (Chrome extension) and an infra product (API). Exciting things coming soon, but this is all that can be shared for now!

To try it, just install the Chrome extension and shop like you normally do. Findcheap will automatically detect when you're on a product page, and proactively offer to help.

A fun experiment is to go through your order history on Amazon, and see how much you could've saved if you installed Findcheap sooner.